Part 1 -Project

The file contains 409 images and labels. Let's view few images and their labels.

Image Pre-Processing

Creating a Mask Detection Model using U-net with MobileNet Transfer Learning Model

Designing Dice Coefficient and Loss function

Compliling the Model

Predicting an image that was not used for training and testing the model

The model was able to detect two faces in the image correctly.

Part 2

Extract the zip file

Function to load images

Define function to load image

Load a sample image

VGG Face model

Load the model

Get vgg_face_descriptor

Generate embeddings for each image in the dataset

Generate embeddings for all images [ Score: 3 points ]

Since all the embedding takes huge time, we can store it local disk and use it wherever necessary

Function to calculate distance between given 2 pairs of images.

Plot images and get distance between the pairs given below

Create train and test sets

Encode the Labels

Standardize the feature values

Reduce dimensions using PCA

Build a Classifier

Test results

Prediction of Test Image 1

Prediction of Test Image 2